WorldCupArena: Instructions file for Claude Code

CLAUDE.md

WorldCupArena CLAUDE.md is an instructions file for Claude Code from wzk1015/WorldCupArena. It costs 604 tokens per session, scanned A, original, MIT.

Project-specific instructions for WorldCupArena, a benchmark that tests language models and research agents on football predictions. They describe the project files, prediction process, and development workflow.

In plain words
What is it for?
Use it when adding models, running prediction experiments, changing the data pipeline, grading results, updating the leaderboard, or running the website locally.
Why use it?
Agents working in an unfamiliar project may otherwise use the wrong files, settings, process, or coding conventions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is wzk1015/WorldCupArena's own configuration. It tells Claude Code how to work on WorldCupArena itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything WorldCupArena configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wzk1015/WorldCupArena. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/wzk1015/WorldCupArena/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/wzk1015/WorldCupArena

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for WorldCupArena CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wzk1015/worldcuparena/claude-md/github.svg)](https://agentmods.dev/instructions/wzk1015/worldcuparena/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/wzk1015/worldcuparena/claude-md"><img src="https://agentmods.dev/badge/instructions/wzk1015/worldcuparena/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for WorldCupArena CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/wzk1015/worldcuparena/claude-md"><img src="https://agentmods.dev/badge/instructions/wzk1015/worldcuparena/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 604 This file is loaded in full into every session.
When invoked 604 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00604 $0.00604
Opus 5 $0.00302 $0.00302
Sonnet 5 $0.00121 $0.00121
Haiku 4.5 $0.00060 $0.00060

Measured 10d ago against content hash f00681e2a369, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

WorldCupArena CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This file provides project-specific context and instructions to Claude.

Project Goal

The primary goal of this project is to benchmark LLMs and deep-research agents on real-world football prediction. This involves everything from predicting the final score to more tactical details like goal scorers and in-match events.

Key Files

  • configs/models.yaml: Contains the list of LLMs and agents being tested. New models can be added here.
  • configs/settings.yaml: Defines the two settings (S1 and S2) for running the models. S1 is for non-tool LLMs with injected context, and S2 is for tool-using models/agents with self-search.
  • src/: The main source code for the project, broken down into ingest, runners, graders, pipeline, and leaderboard.
  • docs/usage.md: Provides a step-by-step guide on how to use the project.
  • docs/integration.md: Explains how to add new models to the benchmark.

Development Process

The lifecycle of a fixture is as follows (LEAD = WCA_PREDICT_LEAD_H, default 48h; set in src/pipeline/scheduler.py):

  1. T-(LEAD+24h): Ingest data (squads, form, news, odds) using ingest.py.
  2. T-LEAD (default T-48h): Lock the snapshot and run predictions for all models. This is also the anti-leakage information horizon (lock_at).
  3. T+3h: Ingest the results of the match.
  4. T+24h: Grade the predictions and build the leaderboard.

Contributions are welcome, especially for new model runners and ingest adapters.

Coding Style

  • The project is written in Python.
  • Follow the existing code structure when adding new features.
  • API keys and other secrets should be stored in a .env file locally and in GitHub Actions secrets for CI.
  • All code should be well-documented.

Running the Website Locally

The project website is a client-side application located in the docs/site/ directory. It works by fetching a data.json file.

To run the full application locally:

  1. Generate the data file: This script collects all the prediction and result data into the JSON file the website needs.
    python3 src/leaderboard/build_site.py
    

Read the full file on GitHub · 49 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 49 lines · 604 tokens per session scan A f00681e2a369

Subscribe to this mod's changes

WorldCupArena CLAUDE.md is an instructions file published in the GitHub repository wzk1015/WorldCupArena (24 stars, last pushed 1mo ago), licensed MIT. It adds 604 tokens to every session, about $0.0030 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens